The pantograph-catenary system (PCS) is the essential power supply in high-speed railway, but its coupling performance influenced significantly by rapidly increasing train speed. actively controlled pantograph one of promising technologies to suppress fluctuation contact force (PCCF). In this paper, we propose a novel control strategy based on deep reinforcement learning (DRL) overcome complex time-varying characteristic PCS, which distorts identification classical methods. First, non-linear...

Active pantograph control is the most promising technique for reducing contact force (CF) fluctuation and improving train's current collection quality. Existing solutions, however, suffer from two significant limitations: 1) they are incapable of dealing with various types, catenary line operating conditions, changing speeds, contingencies well 2) it challenging to implement in practical systems due lack rapid adaptability a new pantograph-catenary system (PCS) conditions environmental...

The sparse direct adaptive equalization technique recently received many attentions for single-carrier underwater acoustic communications. By taking advantage of the (nonuniform) structure a equalizer (DAE), one obtains DAE with improved performance and/or reduced complexity compared its nonsparse counterpart. In this article, is revisited two contributions made: First, comprehensive comparison made existing DAEs designed proportionate-updating (PU) or zero-attracting (ZA) filtering...

In the emerging environment of Internet things (IoT), through connection billions radio frequency identification (RFID) tags and sensors to Internet, applications will generate an unprecedented number transactions amount data that require novel approaches in RFID stream processing management. Unfortunately, it is difficult maintain a distributed model without shared directory or structured index. this paper, we propose fully for federated streams. This combines two techniques, namely, tilted...

The fluctuation of pantograph–catenary contact force seriously affects the current collection quality, maintenance cost, and operation safety high-speed trains. In recent years, agents developed with deep reinforcement learning (DRL) technology have achieved significant success. However, most these jobs are restricted to narrow task distributions stationary environments, which require a large amount training data cannot adapt quickly new task. We propose contrastive learning-based...

Recently, the development of cloud computing has received considerable attention. For service providers, packing VMs onto a small number servers is an effective way to reduce energy costs, so as improve efficiency data center. However allocating too many on physical machine may cause some hot spots which violate SLA applications. Load balancing entire system hence needed guarantee SLA. In this paper, we present simulated-annealing load algorithm for solving resource allocation and scheduling...

With the application of information technology in field education, blended teaching, which integrates advantages traditional teaching and network has attracted increasing attention from academic community at home abroad. Chinese for international students must fully take into account students' instrumental motivation, learning difficulties, behavioral characteristics knowledge structure Chinese, adopt a whole-course, all-area, all-space mode. The "online + offline" can change previous method...

The active pantograph is a promising technology to suppress contact force fluctuation in catenary systems (PCS). Recently, the rapid development of reinforcement learning techniques has dramatically facilitated complex system controllers' design. However, low data efficiency problem fatal because collection costly. In this paper, We propose Ensemble Q-functions Model-based Reinforcement Learning algorithm (EQ-MBRL) achieve data-efficient learning. First, we introduce an ensemble...

In the emerging environment of Internet Things (IoT), through connection billions radio frequency identification (RFID) tags and sensors to Internet, applications will generate an unprecedented number transactions amount data that require novel approaches in mining useful information from RFID trajectories. usually contain a considerable degree uncertainty caused by various factors such as hardware flaws, transmission faults instability. this paper, we propose efficient clustering algorithm...

The vector approximate message passing (VAMP) soft frequency-domain equalizer (SFDE) has been proposed for turbo equalization. It consists of an inner (ISE) and slicer (ISS), which iteratively exchange block-wise extrinsic information to improve the equalization performance, analogous outer iteration between a decoder. However, comparison VAMP-SFDE with other types self-iterative SFDEs, including interference cancellation (SI-BSIC) SFDE generalized (GAMP) SFDE, is lacking. Moreover,...

The ability to track and trace individual items, especially through large-scale distributed networks, is the key realizing many important business applications such as supply chain management, asset tracking, counterfeit detection. Unfortunately, enabling traceability across independent organizations still poses significant challenges in dealing with large volume of data sovereignty participants. This paper describes PeerTrack, a scalable platform for efficiently effectively tracking tracing...

Vertical underwater acoustic (UWA) communications play a crucial role in deep-sea applications. A vertical UWA channel generally features moderate multipath but with time-varying Doppler shifts as well loud impulsive noise. To achieve robust single-carrier communication, this paper proposes an enhanced iterative receiver. First, spline interpolation-based timing estimation approach is proposed to compensate for the effects efficiently. Then, residual errors and interference are tackled by...

Underwater acoustic channels are characterized by a time-varying multipath structure with long delay spread. The is usually very sparse. Direct-adaptation based turbo equalizer low-complexity and effective method to combat the inter-symbol interference caused multipath. This paper studies determinations of tap positions linear equalizers in direct-adaptation multichannel equalizer. A multiple threshold retraining scheme proposed determine sparse position direct-adaptive equalization. length...

In this report, signal processing in underwater acoustic communication system for manned deep submersible “Jiaolong” is introduced. 1. Four methods are integrated to meet different needs: (1) coherent communication, with a variable transmission rate from 5kbps 15kbps, transmit images. (2) Non-coherent 300bps, texts, instructions, and sensor data. (3) Spread spectrum 16bps, instructions. (4) Underwater voice using analogy modulation method human voice. 2. Signal mainly consists of...

The Shipborne acoustic communication system of the submersible Shenhai Yongshi works in vertical, horizontal and slant channels according to relative positions. For ease use, an array combined by a vertical-cone directional transducer horizontal-toroid one is installed on mothership. Improved techniques are proposed combat adverse channel conditions, such as frequency selectivity, non-stationary ship noise, Doppler effects platform's nonlinear movement. coherent modulation, turbo-coded...

With recent advances in technologies such as radio-frequency identification (RFID) and new standards the electronic product code (EPC), large-scale traceability is emerging a key differentiator wide range of enterprise applications (e.g., counterfeit prevention, recalls, pilferage reduction). Such often need to access data collected by individual enterprises distributed environment. Traditional centralized approaches ware-housing) are not feasible for these due their unique characteristics...

Channel equalization plays a crucial role in single-carrier underwater acoustic (UWA) communications. Recently, frequency-domain turbo (FDTE) scheme enabled by the vector approximate message passing (VAMP) algorithm, was proposed, and it outperformed classic linear minimum mean square error FDTE at acceptable complexity cost. The operation of VAMP-FDTE requires knowledge noise power, which is predetermined before starts. In practice, however, difficult to obtain prior power due factors...

For single-carrier underwater acoustic (UWA) communications, a time-domain channel estimation based equalizer (CEE) is usually overlooked in favor of direct adaptive (DAE), mainly due to its high complexity despite potentially better performance. The burden CEE caused by the calculation coefficients, which involves matrix inversion operations at cubic length L. value L for UWA can amount several tens or even hundreds, making scheme prohibitively costly. In this work, with quadratic proposed....